Author:
Zia Ali,Khamis Abdelwahed,Nichols James,Tayab Usman Bashir,Hayder Zeeshan,Rolland Vivien,Stone Eric,Petersson Lars
Abstract
AbstractTopological deep learning (TDL) is an emerging area that combines the principles of Topological data analysis (TDA) with deep learning techniques. TDA provides insight into data shape; it obtains global descriptions of multi-dimensional data whilst exhibiting robustness to deformation and noise. Such properties are desirable in deep learning pipelines, but they are typically obtained using non-TDA strategies. This is partly caused by the difficulty of combining TDA constructs (e.g. barcode and persistence diagrams) with current deep learning algorithms. Fortunately, we are now witnessing a growth of deep learning applications embracing topologically-guided components. In this survey, we review the nascent field of topological deep learning by first revisiting the core concepts of TDA. We then explore how the use of TDA techniques has evolved over time to support deep learning frameworks, and how they can be integrated into different aspects of deep learning. Furthermore, we touch on TDA usage for analyzing existing deep models; deep topological analytics. Finally, we discuss the challenges and future prospects of topological deep learning.
Funder
Australian National University
Publisher
Springer Science and Business Media LLC
Reference102 articles.
1. Adams H, Emerson T, Kirby M, Neville R, Peterson C, Shipman P et al (2017) Persistence images: a stable vector representation of persistent homology. J Mach Learn Res 18(1):218–252
2. Adcock A, Carlsson E, Carlsson G (2016) The ring of algebraic functions on persistence bar codes. Homol Homotopy Appl 18(1):381–402
3. Ali D, Asaad A, Jimenez MJ, Nanda V, Paluzo-Hidalgo E, Soriano-Trigueros M (2023) A survey of vectorization methods in topological data analysis. IEEE Trans Pattern Anal Mach Intell 45(12):14069–14080
4. Amézquita EJ, Nasrin F, Storey KM, Yoshizawa M (2023) Genomics data analysis via spectral shape and topology. PLoS ONE 18(4):e0284820
5. Anirudh R, Venkataraman V, Natesan Ramamurthy K, Turaga P (2016) A riemannian framework for statistical analysis of topological persistence diagrams. In: Conference on computer vision and pattern recognition workshops. pp 68–76
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献